Our new X account is live! Follow @wizwand_team for updates

GUI Grounding on OSWorld-G

72.7Average Score

Qwen3VL-8B-Instruct

Updated 4d ago

Evaluation Results

Method
Qwen3VL-8B-Instruct 2025.12	72.7	82.4	76.7	79.5	61.7	-	-
Qwen3VL-32B-Instruct 2025.12	72	81.6	76.4	77.5	62.4	-	-
Qwen3VL-32B-Instruct 2025.12	71.7	81.6	75.7	77.1	62.4	-	-
UI-Venus-1.5-30B-A3B 2026.02	70.6	-	-	-	-	-	-
UI-Venus-Ground-72B 2025.12	70.4	82.1	71.2	70.7	64.4	-	-
Step-GUI-8B 2025.12	70	-	-	-	-	-	-
UI-Venus-1.5-8B 2026.02	69.7	-	-	-	-	-	-
Qwen3VL-8B-Instruct 2025.12	68.8	79.7	71.8	74.3	59.1	-	-
GTA1-7B 2025.12	68.7	80.8	71.6	71.1	61	-	-
EvoCUA-OpenCUA-72B 2026.01	67.65	-	-	-	-	-	-
MAI-UI-32B 2026.02	67.6	-	-	-	-	-	-
GTA1-7B 2025.12	67.5	80.4	69.4	69.1	60.4	-	-
OpenCUA-72B 2026.01	66.95	-	-	-	-	-	-
Step-GUI-4B 2025.12	66.9	-	-	-	-	-	-
UI-TARS-1.5-7B 2025.12	66.8	78.5	69.1	70	59.7	-	-
GTA1-72B 2025.12	66.7	57.9	76.9	77.3	66.7	-	-
GTA1-32B 2026.02	65.2	-	-	-	-	-	-
Holo2-30B-A3B 2026.02	65.2	-	-	-	-	-	-
Qwen3-VL-32B-Thinking 2026.01	64	-	-	-	-	-	-
EvoCUA-32B 2026.01	63.86	-	-	-	-	-	-
Holo2-8B 2026.02	63.5	-	-	-	-	-	-
Seed1.5-VL 2025.12	62.9	73.9	66.7	69.6	47	-	18.5
GUI-Spotlight 2025.12	62.7	68.2	60.6	63.2	45.6	-	-
UI-Venus-1.0-72B 2026.02	62.2	-	-	-	-	-	-
Qwen2.5-VL-72B 2025.12	62.2	52.6	74.6	74.7	55.3	-	-
UI-TARS-1.5-7B 2025.12	61.9	67.3	64.5	65.2	42.9	-	-
Qwen3-VL-30B-A3B 2026.02	61.2	-	-	-	-	-	-
Qwen3-30B-A3B-Instruct 2025.12	61	-	-	-	-	-	-
Step-GUI-4B 2026.02	60.5	-	-	-	-	-	-
GTA1-7B 2026.02	60.1	-	-	-	-	-	-
MAI-UI-8B 2026.02	60.1	-	-	-	-	-	-
OpenCUA-32B 2026.02	59.6	-	-	-	-	-	-
UI-Venus-1.5-2B 2026.02	59.4	-	-	-	-	-	-
Trifuse+GUI-AIMA 2026.02	58.4	65.6	63.7	69.4	36.3	0.1	-
GUI-AIMA 2026.02	58.3	64.8	65.5	68.8	36.8	-	-
Qwen3-VL-4B-Instruct 2025.12	58.2	-	-	-	-	-	-
Qwen3-VL-8B-Instruct 2025.12	58.2	-	-	-	-	-	-
GUI-Owl-32B 2026.02	58	-	-	-	-	-	-
GUI-Owl-32B 2025.12	58	-	-	-	-	-	-
Trifuse+GUI-Actor 2026.02	57.9	66.4	62.3	67.1	38.9	1.3	-
Qwen3-VL-8B 2026.02	57.5	-	-	-	-	-	-
UI-TARS-72B 2025.12	57.1	69.4	60.6	62.9	45.6	-	-
Qwen3-VL-8B-Thinking 2026.01	56.7	-	-	-	-	-	-
GUI-Actor 2026.02	56.6	65.9	62.7	66.4	38.2	-	-
Trifuse+GUI-Actor 2026.02	56.5	64.9	61.4	66.7	34.4	1.9	-
GUI-Owl-7B 2026.02	55.9	-	-	-	-	-	-
GUI-Owl-7B 2025.12	55.9	-	-	-	-	-	-
OpenCUA-7B 2026.02	55.3	-	-	-	-	-	-
EvoCUA-8B 2026.01	55.08	-	-	-	-	-	-
GUI-Actor 2026.02	54.6	64.4	60.6	64.8	33.6	-	-
UI-Venus-1.0-7B 2026.02	54.6	-	-	-	-	-	-
JEDI 2026.02	54.1	65.9	55.5	57.7	46.9	-	-
Jedi-7B 2025.12	54.1	65.9	55.5	57.7	46.9	-	7.4
UI-TARS-1.5-7B 2026.02	52.8	-	-	-	-	-	-
MAI-UI-2B 2026.02	52	-	-	-	-	-	-
JEDI 2026.02	50.9	67.4	53	53.8	44.3	-	-
Qwen3-VL-2B 2026.02	47.7	-	-	-	-	-	-
UI-TARS 2026.02	47.5	60.2	51.8	54.9	35.6	-	-
UI-TARS-1.5-7B 2025.12	47.5	-	-	-	-	-	-
Gemini-2.5-Pro 2026.02	45.2	59.8	45.5	49	33.6	-	-
Gemini-2.5-pro 2025.12	45.2	59.8	45.5	49	33.6	-	38.9
Trifuse 2026.02	43.6	65.3	35.9	50.4	27.2	18.3	-
InternVL3.5-30B-A3B-Instruct 2025.12	42.4	-	-	-	-	-	-
Operator 2026.02	40.6	51.3	42.4	46.6	31.5	-	-
Operator 2025.12	40.6	51.3	42.4	46.6	31.5	-	-
Trifuse 2026.02	38.7	55.2	33	45.6	24.7	13.4	-
Aguvis-7B 2025.12	38.7	55.9	41.2	43.9	28.2	-	-
UGround-V1 2026.02	36.4	51.3	40.3	43.5	24.8	-	-
OpenAI CUA 2025.12	36.4	-	-	-	-	-	-
UGround-V1-7B 2025.12	36.4	51.3	40.3	43.5	24.8	-	-
Qwen2.5-VL 2026.02	31.4	45.6	32.7	41.9	18.1	-	-
OS-Atlas-7B 2025.12	27.7	44.1	29.4	35.2	16.8	-	7.4
Qwen2.5-VL 2026.02	27.3	41.4	28.8	34.8	13.4	-	-
TAG 2026.02	25.3	44.9	19.2	28.1	8.4	-	-